Conference Paper

Fuel Oil Consumption Prediction Model for AI Optimisation Platform

September 15–16, 2026 SOME Conference, Athens 18 min read

Abstract

An ANN-based fuel-consumption model trained on four years of vessel telemetry. Voyage segmentation, drifting/canal/port removal, and fuel-type filtering produce a clean RPM signal that drives the prediction layer.

"The work on voyage segmentation, drifting/canal/port removal, fuel type filtering produced a clean RPM signal."

The work in plain English

This paper is one piece of the verification chain behind the VF Engine. Every recommendation a fleet operator sees in production traces back to a body of work like this one — published, peer-reviewed where applicable, and signed by named authors who can be reached for follow-up.

The full technical paper, including figures, tables, and the methodological appendix, is available on request. We are happy to walk through the work with technical buyers, charter parties, and underwriters who want to verify what the system actually does.

Where this lives in the engine

The findings in this paper inform foc decisions inside the routing pipeline. For the full picture of how data flows from sensor to bridge, see The VF Engine. For verified outcomes built on this methodology, see Case Studies.

How to get the full paper

Email info@vesselfront.com with the paper title and your role. Closed-beta operators get full access automatically.

Bring the methodology to your fleet

Closed beta admits operators on a rolling basis. The trial voyage is free.